From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=100.103.45.18 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1794969550; b=pDxXzQQ4Pb9gCZvBP8rgvJgA7gtFuisU9ZHcsWzdfYcuXRM15OFN5p5OJSgmmnnCyZg0 FmDc0Nm+srv/wI7tYXJ0TiEGxEiMT59VLwFY8wZY+rNXvLjl9+BcitxzZ6f1twAkyLxsn pd58K4dSpnT1TKli8c3mcdrs4L6uTkZ4W1Db0DNTcgUvKVmbyj6xc4wkRuHFVsCvi+7qn pkXWXbZnHJQk/krm3T1O+2l9ofims67DXGlRRcKhLkXBi/dX+dcLrBf7n/gahv7rASptt LxkWk9ERqW/d1vePPZWz4+d9GTUZWhUKLLaLVOB77WMCbVuqVlUWTegYFtn3wwHCVhA== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1794969550; h=Received:DKIM-Signature:From:To:Cc:Subject:Date:Message-ID:X-Mailer: In-Reply-To:References:MIME-Version:Content-Transfer-Encoding; bh=2+j5rQVeZEKVIp6UipLUZTq7yK+iygfHcnnhiMmH55o=; b=26VOWh6YPdualMZLnb0bq1ChwIMyFDS63CGbBCAzK8x4WHQACiMBd9DU4Ri6EAkl7/q7 8iVuDyN5eRV0x+KszlBrPYM7whPQyrMCj55wyZAvLlY52DF1CvLkpeayr0nkLBiPG0fHL j8CW/oy25WcTkOaEosWlNwfVVWeGYY0eMGobzhFL96I8dTqUYMARsQGmM1WLoumDMpouX 1uyqmNzK3xLYfkSlkt7OQsqjEB1sTQ6kXsixuScWESFwmXhvcVrdq1zdndAm3qNaq7N05 YrVg+BfyDsmmOFlXRBFwmIrUqsoyzgn8ODOKz8IBK5N2D4LSXDq6AqBVJr+2M/R0HQg== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256 header.s=k20260515 header.b=EhoSEbo0; arc=none smtp.remote-ip=100.103.45.18 Received: from smtp.kernel.org (quasi.space.kernel.org [100.103.45.18]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id DF2A2606A337 for ; Wed, 18 Nov 2026 02:39:10 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256 header.s=k20260515 header.b=EhoSEbo0 Received: by smtp.kernel.org (Postfix) with ESMTPSA id 379341F000C5; Wed, 18 Nov 2026 02:39:10 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1794969550; bh=2+j5rQVeZEKVIp6UipLUZTq7yK+iygfHcnnhiMmH55o=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=EhoSEbo0AIM+wdEJ2Jiu+/eUjGOuwAtsX3DXioHn0tUoydZIZBkF1K+0n2iCD4er8 GAL0hY65jz1vg3ZFFXCJUAQPywEeve1VmWXnFWRR1kqMLtzDU3xwavAx0p1WA0AXHt Cj0mAZ4Y2I9bfFibqDZkvo8mleqiWcLlYX6VWMnWaOnJA+oFBvxvzbjE++yT28ASkE 7yAo1NO779+Zu7lEZczqftGCx0ZEbm2TawsoCIeeDBRpQn+OBfQN+Lg3+7+iYObPI9 vP3KDNNOM4Ve1gZPeajM5moqz9M3PCGNXrev52NvjhwoDw//0Tq26DbFQRmnVjwvsi cKb7fnCkh2E3A== From: Jakub Kicinski To: davem@davemloft.net, michael.chan@broadcom.com Cc: netdev@vger.kernel.org, edumazet@google.com, pabeni@redhat.com, andrew+netdev@lunn.ch, horms@kernel.org, pavan.chebbi@broadcom.com, Jakub Kicinski Subject: [PATCH net-next 2/6] eth: bnxt_en: follow explicitly set IRQ affinity when placing page pool Date: Tue, 17 Nov 2026 18:39:01 -0800 Message-ID: <20261118023905.3050661-3-kuba@kernel.org> X-Mailer: git-send-email 2.56.1 In-Reply-To: <20261118023905.3050661-1-kuba@kernel.org> References: <20261118023905.3050661-1-kuba@kernel.org> X-Mailing-List: netdev@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-Transfer-Encoding: 8bit The driver picks the NUMA node for each Rx ring's page pool with cpumask_local_spread() at open. IRQ affinity configured by the user is already recorded by the driver and persists across close/open cycles. Use it instead of cpumask_local_spread(). The affinity notifier runs without any of the locks held by the allocation paths, and copying a multi-word cpumask is not atomic. Like for the TPH Steering Tag, have the notifier compute the node (of the first online CPU in the mask) and publish it with WRITE_ONCE(). Queue restart (bnxt_queue_mem_alloc()) needs to resolve the NUMA node instead of copying the nid of the old page pool. Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 5 +++ drivers/net/ethernet/broadcom/bnxt/bnxt.c | 48 +++++++++++++++++++---- 2 files changed, 46 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 41d05efd6307..86fc2e8a5816 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2488,6 +2488,11 @@ struct bnxt { * rather than being our own default placement. */ unsigned long *ring_affinity_set; + /* Node of the first online CPU in the mask configured from + * the outside, NUMA_NO_NODE if none. Written by the affinity + * notifier, read locklessly by the allocation paths. + */ + int *ring_nid; int max_irqs; int total_irqs; int ulp_num_msix_want; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 5ad2a3033505..8e8ee02ca8d9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3818,6 +3818,21 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem) return 0; } +/* Node of the CPU expected to service cp ring @n. If the IRQ affinity was + * configured from the outside (by the user or irqbalance) the affinity + * notifier recorded the node to use, otherwise follow our default spread. + */ +static int bnxt_cp_num_to_node(struct bnxt *bp, int n) +{ + int nid = READ_ONCE(bp->ring_nid[n]); + unsigned int cpu; + + if (nid != NUMA_NO_NODE) + return nid; + cpu = cpumask_local_spread(n, dev_to_node(&bp->pdev->dev)); + return cpu_to_node(cpu); +} + static void bnxt_free_one_tpa_info(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) { @@ -4020,8 +4035,7 @@ static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp, struct bnxt_rx_ring_info *rxr static int bnxt_alloc_rx_rings(struct bnxt *bp) { - int numa_node = dev_to_node(&bp->pdev->dev); - int i, rc = 0, agg_rings = 0, cpu; + int i, rc = 0, agg_rings = 0; if (!bp->rx_ring) return -ENOMEM; @@ -4036,8 +4050,7 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp) ring = &rxr->rx_ring_struct; - cpu = cpumask_local_spread(i, numa_node); - cpu_node = cpu_to_node(cpu); + cpu_node = bnxt_cp_num_to_node(bp, i); netdev_dbg(bp->dev, "Allocating page pool for rx_ring[%d] on numa_node: %d\n", i, cpu_node); rc = bnxt_alloc_rx_page_pool(bp, rxr, cpu_node); @@ -11870,6 +11883,8 @@ static void bnxt_irq_affinity_notify(struct irq_affinity_notify *notify, const cpumask_t *mask) { struct bnxt_irq *irq; + unsigned int cpu; + int nid; u16 tag; irq = container_of(notify, struct bnxt_irq, affinity_notify); @@ -11877,6 +11892,14 @@ static void bnxt_irq_affinity_notify(struct irq_affinity_notify *notify, cpumask_copy(irq->bp->ring_cpu_mask[irq->ring_nr], mask); set_bit(irq->ring_nr, irq->bp->ring_affinity_set); + /* Allocation paths don't hold any lock which would exclude us, + * publish the node to allocate on instead of making them parse + * the mask while it may be getting overwritten. + */ + cpu = cpumask_first_and(mask, cpu_online_mask); + nid = cpu < nr_cpu_ids ? cpu_to_node(cpu) : NUMA_NO_NODE; + WRITE_ONCE(irq->bp->ring_nid[irq->ring_nr], nid); + #ifdef CONFIG_RFS_ACCEL if (irq->bp->dev->rx_cpu_rmap && irq->ring_nr < irq->bp->rx_nr_rings) { int err; @@ -11954,9 +11977,16 @@ static int bnxt_alloc_ring_cpu_masks(struct bnxt *bp) if (!bp->ring_affinity_set) return -ENOMEM; - for (i = 0; i < bp->max_irqs; i++) + bp->ring_nid = kmalloc_array(bp->max_irqs, sizeof(*bp->ring_nid), + GFP_KERNEL); + if (!bp->ring_nid) + return -ENOMEM; + + for (i = 0; i < bp->max_irqs; i++) { if (!zalloc_cpumask_var(&bp->ring_cpu_mask[i], GFP_KERNEL)) return -ENOMEM; + bp->ring_nid[i] = NUMA_NO_NODE; + } return 0; } @@ -11971,6 +12001,8 @@ static void bnxt_free_ring_cpu_masks(struct bnxt *bp) for (i = 0; i < bp->max_irqs; i++) free_cpumask_var(bp->ring_cpu_mask[i]); + kfree(bp->ring_nid); + bp->ring_nid = NULL; bitmap_free(bp->ring_affinity_set); bp->ring_affinity_set = NULL; kfree(bp->ring_cpu_mask); @@ -12066,6 +12098,7 @@ static int bnxt_request_irq(struct bnxt *bp) if (!test_bit(i, bp->ring_affinity_set) || !cpumask_intersects(cpu_mask, cpu_online_mask)) { clear_bit(i, bp->ring_affinity_set); + WRITE_ONCE(bp->ring_nid[i], NUMA_NO_NODE); cpumask_clear(cpu_mask); cpumask_set_cpu(cpumask_local_spread(i, numa_node), cpu_mask); @@ -16431,7 +16464,7 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, struct bnxt_rx_ring_info *rxr, *clone; struct bnxt *bp = netdev_priv(dev); struct bnxt_ring_struct *ring; - int rc; + int nid, rc; if (!bp->rx_ring) return -ENETDOWN; @@ -16452,7 +16485,8 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, clone->rx_tpa = NULL; clone->rx_tpa_idx_map = NULL; - rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid); + nid = bnxt_cp_num_to_node(bp, idx); + rc = bnxt_alloc_rx_page_pool(bp, clone, nid); if (rc) return rc; -- 2.56.1